FragGT: Fragment-based evolutionary molecule generation with gene types

In this paper, from the point of view reducing the system calculation cost, a digital channelized receiver is proposed. The decimation factor of the proposed digital channelized receiver with low calculation cost is equal to the number of signal channels, which is acquired by changing the input signal of the embedded instantaneous frequency measurement receiver. Due to the increase of the system decimation factor, the data to be processed are decreased and the system processing speed is improved indirectly. In this paper, the architecture and working principle of the proposed digital channelized receiver with low calculation cost is firstly given; secondly, the overlapping channel division method used in the digital channelized receiver with low calculation cost is put forward. Meanwhile, the channel arbitration method of the unmodulated or modulated signal in the case of overlapping channel division is analyzed. Then, the frequency measurement principle of the embedded instantaneous frequency measurement receiver is deduced in detail. Through the use of the overlapping channel division method, the proposed digital channelized receiver with low calculation cost is able to avoid the existence of blind spots between channels and increases the interception probabilities of the input signals. And, the proposed digital channelized receiver can distinguish two signals coming simultaneously to the same channel by using the overlapping channel division method. In addition, the channel of the input signal truly residing can be simply determined by using the channel arbitration in the case of overlapping channel division and according to the output frequency of the embedded instantaneous frequency measurement receiver. Finally, the related simulation results verify the correctness and feasibility of the theories and method involved in this paper.

Disentangled convolution for optimizing receptive field

Here, analytical studies have been carried out to determine the optimal values of effective parameters on the stress concentration factor around a cutout using genetic algorithm. Optimum designs of single lamina as well as symmetric laminates with 4, 8 and 12 layers of graphite/epoxy and glass/epoxy plates containing a circular cutout with various sizes are presented. The work focuses on extending the analytical solution given by Greszczuk to determine the stress distribution in multilayered composite plates subjected to arbitrary in-plane loadings. This is achieved by introducing an arbitrary oriented uniaxial, biaxial and shear loading conditions into Greszczuk solution. In order to mimic as much as possible the real structural behavior, the finite-width correction factor given by Tan is used. Effective parameters on stress distribution around the circular cutout in composite plates considered as design variables include: load angle, fiber orientation, cutout size and stacking sequence of the laminate. The objective function in this study is the minimization of maximum stress concentration around the cutout which is calculated by the present analytical solution. The first ply failure load predicted using Tsai–Wu criterion is maximized for both single lamina and symmetric laminates. Also, the weight of the plates is minimized by increasing the hole size to width ratio. The results obtained by the present analytical solution compare favorably with those obtained using complex variable method. For laminated plate subjected to shear loading, the stress concentration factor decreased drastically by 48.79% compared to a single lamina. The failure load is also increased in most of the loading cases. The results also showed that the genetic algorithm code converges rapidly in most of the cases. The accuracy, quickness, low computational cost and the simplicity of the present solution encourage the designers to use it in practical applications.

Cumulative residual Kullback-Leibler divergence based sensor placement using reliability criteria

A drug takes many years to develop and reach the market using the conventional drug discovery procedure. Computer-aided drug design (CADD) is an emerging technology that accelerates the process of drug discovery and minimizes the total expenditure associated with labour and resources. In the current scenario, the computational aided drug design (CADD) techniques play a significant role in the design and development of lead molecules for the treatment of various lethal pathological conditions. The prediction of the tertiary structure of a protein is a big concern in drug design and discovery. A typical drug discovery procedure starts with the tertiary structure of a protein. At present, a total of 184,407 protein structures are available in the protein data bank, which are determinedusing experimental methods. However, the procedures are difficult and time-consuming. A more advanced technique has been developed for the prediction of the 3D structure of a protein using a computational method. This technique has played a vital role in drug discovery. It has not only facilitated but also hastened the process of drug discovery. The method is named homology modeling since it involves the building of a protein model based on its homology to similar evolutionary proteins. The method is based on the fact that evolutionary related proteins have similar structures. In homology modelling, the 3D structure of a protein is derived from its primary sequence based on its similarity to the existing protein templates. There are many computational tools for homology modelling such as Modeller, Swiss model, Composer, 3D-JIGSAW, etc. The proposed book chapter will cover the introduction to homology modelling, step-by-step guide to building a protein model, various challenges and how to refine and validate the model, different algorithms related to sequence alignment, similarity search, and the applications of homology modelling in drug design and discovery. The chapter would be very fruitful to the readers to get insights into protein modelling, which will facilitate their research activities. It will be of great application in various disciplines,such as bioinformatics, physics, structural biology, and molecular biology. The content of the chapter will cover various research papers, review papers, and corresponding reference books.

Astronomical images are usually assumed to be corrupted by a space-invariant Point Spread Function and Poisson noise. In this paper we propose an original projected inexact Newton method for the solution of the constrained nonnegative minimization problem arising from image deblurring. The problem is ill-posed and the objective function must be regularized. The inner system is inexactly solved by few Conjugate Gradient iterations. The convergence of the method is proved and its efficiency is tested on simulated astronomical blurred images. The results show that the method produces good reconstructed images at low computational cost.

In this article, a new methodology for sensitivity analysis evaluation of electric potential distribution near transmission lines (TLs) is proposed. The potential is modeled by the finite element method, and the sensitivity related to cable positions is obtained using the adjoint method, and thus the objective function’s sensitivity is adopted during the optimization process using a multiple cuts’ ellipsoid method to get new geometries with high surge impedance loading (SIL). The sensitivities of a large number of conductors by phase are obtained with high precision and very low computational cost, using adjoint sensitivities, which are not dependent on the number of design variables. The approximation using central finite differences (CFDs) to calculate the sensitivity is used for comparisons and validation. Therefore, with this methodology, the finite element method (FEM) model of TLs can be used during the optimization process without compromising the required computational processing time.

A new multi-section based technique for constrained optimization problems with interval-valued objective function

Fish embryo models are used increasingly for human disease modeling, chemical toxicology screening, drug discovery and environmental toxicology studies. These studies are devoted to the analysis of a wide spectrum of physiological parameters, such as mortality ratio. In this article, we develop an assay to determine Medaka (Oryzias latipes) embryo mortality. Based on video sequences, our purpose is to obtain reliable, repeatable results in a fully automated fashion. To reach that challenging goal, we develop an efficient morphological pipeline that analyses image sequences in a multiscale paradigm, from the global scene to the embryo, and then to its heart, finally analysing its putative motion, characterized by intensity variations. Our pipeline, based on robust morphological operators, has a low computational cost, and was experimentally assessed on a dataset consisting of 660 images, providing a success ratio higher than 99%.

Geometric deep learning has been revolutionizing the molecular modeling field. Despite the state-of-the-art neural network models are approaching ab initio accuracy for molecular property prediction, their applications, such as drug discovery and molecular dynamics (MD) simulation, have been hindered by insufficient utilization of geometric information and high computational costs. Here we propose an equivariant geometry-enhanced graph neural network called ViSNet, which elegantly extracts geometric features and efficiently models molecular structures with low computational costs. Our proposed ViSNet outperforms state-of-the-art approaches on multiple MD benchmarks, including MD17, revised MD17 and MD22, and achieves excellent chemical property prediction on QM9 and Molecule3D datasets. Furthermore, through a series of simulations and case studies, ViSNet can efficiently explore the conformational space and provide reasonable interpretability to map geometric representations to molecular structures.

Accurate prediction of compound-protein interactions (CPIs) is crucial for chemical biology and drug discovery. Despite recent advancements, existing deep learning (DL)-based CPI models often struggle to simultaneously achieve high generalization performance, quantify prediction confidence, and ensure explainability. Here, we propose ChemGLaM, a chemical genomics language model designed to address these three crucial challenges, thereby enabling reliable and explainable CPI predictions. ChemGLaM integrates independently pre-trained chemical and protein language models through an interaction block with a cross-attention mechanism, achieving near state-of-the-art performance in predicting novel CPIs at a low computational cost. Incorporating uncertainty estimation and attention visualization enables ChemGLaM to enhance the success rate of virtual screening and to provide molecular insights into CPIs. To demonstrate the practical impact of ChemGLaM, we constructed a publicly available database containing large-scale CPI predictions for every possible pairing between all 20,434 human proteins and all 11,455 drugs and validated its practical applicability in a case study on amyotrophic lateral sclerosis. ChemGLaM marks an important step forward in addressing the challenges of AI-driven CPI exploration and drug discovery.Scientific ContributionThis study established a unified CPI prediction framework that simultaneously achieves high generalization performance, confidence quantification, and explainability. We leveraged this framework to create a community resource by constructing a comprehensive CPI database and demonstrated its practical utility by successfully prioritizing hit compounds and deconvoluting their targets in a phenotypic screening for amyotrophic lateral sclerosis.

Aliasing in computer-synthesized images not only limits the realism of the images, but also affects the user's concentration. Many antialiasing methods have been proposed to solve this problem, but almost all of them are computation intensive, and some of them are also memory intensive. While these may not be limitations for high-end applications such as medical visualization and architectural design, this kind of antialiasing methods may still be far too costly for the low-cost applications. In this paper, we propose an antialiasing method that operates in the image domain. It is based on fitting curves to the discontinuity edges extracted from the aliased images to reshade those edge pixels. (Note that a curve may be considered as a general form of lines.) To improve the performance and the simplicity of the method, we propose to preprocess all possible edge patterns and fit curves in advance. During runtime, we only need to construct an index to obtain the filtering information from a lookup table. The new method is extremely simple and efficient. It provides a very good compromise between hardware cost and output image quality. In addition, because the new method has a very low computational cost, and hence low power consumption for hardware implementation, it is particularly suitable for low-cost mobile applications such as computer game consoles and palm computers, where low implementation cost and low power consumption are important design factors.

Accurate needle placement is essential for prostate biopsy. Recently, transperineal prostate biopsies are receiving renewed interest due to concern over infection from conventional transrectal biopsies. However, accurate needle placement is more challenging in the transperineal approach than in the transrectal approach due to the long insertion distance leading to a large targeting error and repeated insertion attempts. Improved procedure planning tools that can predict the deviation of the needle can potentially reduce the targeting error and number of insertion attempts. Prediction of deflection magnitude requires a model of biopsy needle deflection, which in turn requires information about tissue material properties. However, material properties of tissue in patients cannot be easily obtained. Accounting for this uncertainty in patient tissue properties requires a model capable of quantifying uncertainty in needle deflection as a function of a distribution of tissue properties. A Monte Carlo uncertainty quantification requires 1000s of samples, but it is not possible to obtain this many samples in a short enough time for intraoperative procedure planning using published needle deflection predictionmodels. This work seeks to develop a model of needle deflection fast enough for use in intraoperative procedure planning, validate this model against experimental results, and integrate it into a Monte Carlo uncertainty quantificationmodel. This work used a mechanics-based model of biopsy needle deflection to train a Fourier feature neural network (FFNN) model in order to make predictions with a low computational cost. Both models were validated against experimental data. The neural network model was used in a Monte Carlo uncertainty quantification model to quantify uncertainty in needle deflection arising from uncertain tissue mechanicalproperties. This work (1) implemented a mechanics-based model and a FFNN model. Both models were validated against previously published experiments carried out with tissue phantoms. Both models showed close agreement with the experimental data. (2) We showed that our FFNN model was more accurate than a baseline ordinary least squares model, introducing only about 0.3-mm tip deflection error compared to the mechanics-based model. We also showed that our FFNN model makes unbiased predictions with respect to the amount of deflection. (3) We demonstrated a Monte Carlo uncertainty quantification model of needle deflection with a low computational cost of about 20 CPU s. We used our uncertainty quantification model to show how the depth, stiffness, and magnitude of uncertainty in a layer of tissue affect needle deflection. In addition, we showed a simple clinical example of the use of our model. This work demonstrates a Monte Carlo uncertainty quantification model of needle deflection with a low computational cost. This method shows promise for future applications in procedure planning for prostate biopsies as well as other transperineal procedures conducted with flexible needles such as cryoablation andbrachytherapy.

Given the adverse impact and unnecessary costs associated with harmonic pollution in electrical power systems, such as increasing losses and decreasing life expectancy of equipment, development of new filtering techniques with higher quality of power, higher efficiency of transmission and distribution, and lower cost of filters is urgently required. This has become all the more important as society increasingly moves towards an environment filled with sophisticated electronic equipment and power-sensitive electrical machinery. The present work was conceived to provide a way forward towards the goal of improving Power Quality (PQ) by designing a new passive shunt filter based on minimizing the responsibility of the consumer for harmonic pollution, while simultaneously taking into account other relevant objective functions and related techno-economic considerations. Shunt passive filters are commonly found in power industries, where quality of power is paramount, in view of their simplicity of design, lower cost and their having possibly different range of frequency response characteristics that can satisfy a specific harmonic filtering needs. In addition, passive filters, in general, have two primary favourable features, they support reactive power to correct the load power factor and they mitigate harmonic distortion. This study favours passive filters while conceptualizing the research problem and formulating a proposed design. This thesis presents an optimal design of single-tuned passive filters that mm1m1zes consumer's responsibility for harmonic pollution. A solution for the allocation ofresponsibility between supplier and consumer has proved complex and elusive and it remains, therefore, absent. When, whoever takes whatever steps to contain the harmonic distortion, involves costs and expenditure, the situation inevitably leads to conflict between consumer and utility. In order to avoid this unwholesome state of affairs and introduce a degree of rationality and clarity, this study focuses on quantifying harmonic pollution responsibility by substantiating a new "NonLinearity Current Index" (NLCI) and presenting the mathematical modelling of the filter accordingly. The task of designing the filter, then, is posed as a quadratic optimization problem with nonlinear constraints, whose objective function includes the newly proposed NLCI, which will be minimized, as well as five other conventional objective functions that are most frequently used in the design of passive filters. The five objective functions are: i. maximization ofload power factor; ii. Minimization of the voltage total harmonic distortion; iii. minimization of the current total harmonic distortion; iv. minimization of transmission loss; and v. minimization of the filter investment cost. A suitable analytic framework is established, in which circuit analysis is made and relevant auxiliary mathematical expressions are derived for the system under study, followed by the filter design problem posed as an optimization question with the required objective functions and constraints. This thesis uses FORTRAN Feasible Sequential Quadratic Programming (FFSQP) to obtain the optimal values for the single-tuned shunt passive filter elements. The performance of the proposed index and the other five conventional objective functions is evaluated using six numerical 'benchmark' case studies to demonstrate the applicability, viability, validity and usefulness of the proposed harmonic passive filters. A rigorous and thorough comparison of the results of the design with and without compensation is included. As resonance is a critical design issue of passive filters, special care was taken, during the problem formulation, to avoid any risk of it in the compensated system. Care was also taken to meet capacitor loading specifications as given in IEEE Standard 18-2012 and practical constraints for the voltage total and individual harmonic distortion limits were followed in accordance with IEEE 519-2014 guidelines. The results of this study demonstrate the validity and effectiveness of the optimization method, for the given objective functions, since improvements were seen in both power factor and displacement power factor in all the case studies as well as notable reductions in rms values of the line current which led to reduced transmission losses, voltage drop and increased transmission efficiency, to various degrees and in a variety of combinations. Incorporation of the newly designed passive filter resulted in a considerable reduction in NLCI, indicating increased linearity because of minimization of the difference between supply current rms and linear current m1s at the point of common coupling. Critical impedance values also improved, because of the greatly reduced m1s line current. The NLCI minimised passive filter design differentiates the contributions of the supplier and consumer to harmonic pollution in a given system, and, therefore, provides a valuable solution where currently there is none in the literature, reflected in the absence of recognised standards and methodologies in this area. The small size of the proposed filter, in comparison to many other published designs, entails considerably lower financial investment costs, which, combined with its effectiveness at reducing harmonic pollution makes it a very valuable contribution to power system design and installation.

A simplified hindcast method for the estimation of extreme storm surge events in semi-enclosed basins